Primary sourcelmarena.ai
View sourceEvent ·Multi-source
Claude Opus 5.5 上线 Agent Arena,可投票实测智能体任务
Anthropic 的 Claude Opus 5.5 现已加入 Agent Arena 排行榜,该榜单基于数百万条真实用户提交的长程智能体任务,模型可调用网页搜索、文件系统和终端工具完成复杂工作流。排行榜采用因果追踪方法,以相对平均模型的结果表现来计分。除了 Agent Arena,Opus 5.5 还进入了 WebDev、Text、Vision 和 Document 四个赛道的 Battle Mode。官方称其在多数任务上达到 Claude Fable 5.1 水平,运行成本比 Opus 5 低 40%。
Current read
Claude Opus 5.5 进 Agent Arena 了,你的 toughest prompt 能直接给模型出难题投票,还能看到它在 WebDev、Vision 等赛道的对战成绩。
11 sources83° AI heatLast updated 2026/9/22 17:48:17
Evidence
11 sourcesRelated source 1宝玉
View sourceRelated source 2Artificial Analysis
View sourceRelated source 3Claude
View sourceRelated source 4Decoder
View sourceRelated source 5Anthropic
View sourceRelated source 6Alex Albert
View sourceRelated source 7歸藏(guizang.ai)
View sourceRelated source 8OpenRouter
View sourceRelated source 9The Rundown AI
View sourceRelated source 10Aravind Srinivas
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.